Zobrazeno 1 - 10
of 911
pro vyhledávání: '"Tay Wee"'
Place recognition plays a crucial role in the fields of robotics and computer vision, finding applications in areas such as autonomous driving, mapping, and localization. Place recognition identifies a place using query sensor data and a known databa
Externí odkaz:
http://arxiv.org/abs/2410.04939
We introduce a novel uncertainty principle for generalized graph signals that extends classical time-frequency and graph uncertainty principles into a unified framework. By defining joint vertex-time and spectral-frequency spreads, we quantify signal
Externí odkaz:
http://arxiv.org/abs/2409.04229
We consider a multiple hypothesis testing problem in a sensor network over the joint spatial-time domain. The sensor network is modeled as a graph, with each vertex representing a sensor and a signal over time associated with each vertex. We assume a
Externí odkaz:
http://arxiv.org/abs/2408.03142
Personalized subgraph Federated Learning (FL) is a task that customizes Graph Neural Networks (GNNs) to individual client needs, accommodating diverse data distributions. However, applying hypernetworks in FL, while aiming to facilitate model persona
Externí odkaz:
http://arxiv.org/abs/2405.16056
This work introduces two novel neural spike detection schemes intended for use in next-generation neuromorphic brain-machine interfaces (iBMIs). The first, an Event-based Spike Detector (Ev-SPD) which examines the temporal neighborhood of a neural ev
Externí odkaz:
http://arxiv.org/abs/2405.08292
Autor:
Kang, Qiyu, Zhao, Kai, Ding, Qinxu, Ji, Feng, Li, Xuhao, Liang, Wenfei, Song, Yang, Tay, Wee Peng
We introduce the FRactional-Order graph Neural Dynamical network (FROND), a new continuous graph neural network (GNN) framework. Unlike traditional continuous GNNs that rely on integer-order differential equations, FROND employs the Caputo fractional
Externí odkaz:
http://arxiv.org/abs/2404.17099
Autor:
She, Rui, Kang, Qiyu, Wang, Sijie, Tay, Wee Peng, Zhao, Kai, Song, Yang, Geng, Tianyu, Xu, Yi, Navarro, Diego Navarro, Hartmannsgruber, Andreas
Point cloud registration is a fundamental technique in 3-D computer vision with applications in graphics, autonomous driving, and robotics. However, registration tasks under challenging conditions, under which noise or perturbations are prevalent, ca
Externí odkaz:
http://arxiv.org/abs/2404.14034
Autor:
Kang, Qiyu, Zhao, Kai, Song, Yang, Xie, Yihang, Zhao, Yanan, Wang, Sijie, She, Rui, Tay, Wee Peng
In this work, we rigorously investigate the robustness of graph neural fractional-order differential equation (FDE) models. This framework extends beyond traditional graph neural (integer-order) ordinary differential equation (ODE) models by implemen
Externí odkaz:
http://arxiv.org/abs/2401.04331
Autor:
She, Rui, Wang, Sijie, Kang, Qiyu, Zhao, Kai, Song, Yang, Tay, Wee Peng, Geng, Tianyu, Jian, Xingchao
Publikováno v:
Proceedings of the AAAI Conference on Artificial Intelligence (AAAI 2024), Vancouver, Canada, 2024
Point cloud registration is a crucial technique in 3D computer vision with a wide range of applications. However, this task can be challenging, particularly in large fields of view with dynamic objects, environmental noise, or other perturbations. To
Externí odkaz:
http://arxiv.org/abs/2401.03167
The utilization of multi-modal sensor data in visual place recognition (VPR) has demonstrated enhanced performance compared to single-modal counterparts. Nonetheless, integrating additional sensors comes with elevated costs and may not be feasible fo
Externí odkaz:
http://arxiv.org/abs/2312.10616